用多阶段非确定性方法提升图数据高阶特征分类准确率
Multistage non-deterministic classification using secondary concept graphs and graph convolutional networks for high-level feature extraction
- 分三步：先用GCN提取12个高阶特征，再用不完全模型处理，最后逻辑图定论
- 在Cora、Citeseer、PubMed上分别达到96%、93%、95%准确率
- 适合处理复杂关系图数据的分类任务，尤其关注特征提取与推理过程
图由节点和边构成，直观展现关系与结构，但其复杂连接给高阶特征提取带来挑战，节点权重对某些特征影响更大。在多元主题领域，图可表征特征间关联，而图内模式发现被证明是NP难问题。图卷积网络（GCNs）是利用节点连通性与属性获取有意义表征的主流深度学习方法。尽管成果显著，但预测9个确定类别常出现误差。为此，本文提出基于次级概念图与图卷积网络的多阶段非确定性分类方法，包含三个步骤：1）利用GCN提取并生成12个高阶特征；2）在最终判定前采用不完整、非确定性模型进行特征提取；3）基于概念（逻辑）图做出最终预测。实验结果表明，该方法在分类任务中优于现有技术，在Cora、Citeseer、PubMed三个数据集上的准确率分别为96%、93%、95%。代码已开源：https://github.com/MasoudKargar。
原文摘要 · Abstract (English)
Graphs, comprising nodes and edges, visually depict relationships and structures, posing challenges in extracting high-level features due to their intricate connections. Multiple connections introduce complexities in discovering patterns, where node weights may affect some features more than others. In domains with diverse topics, graph representations illustrate interrelations among features. Pattern discovery within graphs is recognized as NP-hard. Graph Convolutional Networks (GCNs) are a prominent deep learning approach for acquiring meaningful representations by leveraging node connectivity and characteristics. Despite achievements, predicting and assigning 9 deterministic classes often involves errors. To address this challenge, we present a multi-stage non-deterministic classification method based on a secondary conceptual graph and graph convolutional networks, which includes distinct steps: 1) leveraging GCN for the extraction and generation of 12 high-level features: 2) employing incomplete, non-deterministic models for feature extraction, conducted before reaching a definitive prediction: and 3) formulating definitive forecasts grounded in conceptual (logical) graphs. The empirical findings indicate that our proposed approach outperforms contemporary methods in classification tasks. Across three datasets Cora, Citeseer, and PubMed the achieved accuracies are 96%, 93%, and 95%, respectively. Code is available at https://github.com/MasoudKargar.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。